ClawHub
Back to skill

Security audit

AI Prompt Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local prompt-template generator with some broad wording and Chinese-only output, but no hidden access, persistence, network use, or destructive behavior.

Install only if you want a mostly Chinese-language command-line helper for generating AI prompts. Be aware that its activation wording is broad, so users may want to invoke it only when explicitly asking for prompt generation or prompt analysis.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
length=length_desc
    )
    
    return prompt

def generate_chatgpt_prompt(role, task, context="", constraints=""):
    """生成ChatGPT专用提示词"""
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
length=length_desc
    )
    
    return prompt

def generate_chatgpt_prompt(role, task, context="", constraints=""):
    """生成ChatGPT专用提示词"""
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
length=length_desc
    )
    
    return prompt

def generate_chatgpt_prompt(role, task, context="", constraints=""):
    """生成ChatGPT专用提示词"""
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
length=length_desc
    )
    
    return prompt

def generate_chatgpt_prompt(role, task, context="", constraints=""):
    """生成ChatGPT专用提示词"""
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill description is extremely broad and includes catch-all phrasing such as 'any AI prompt engineering needs,' which can cause the skill to activate for a wide range of generic requests unrelated to a narrowly scoped capability. In agent environments, this increases the chance of over-triggering, unintended prompt interception, and unnecessary exposure of user inputs to this skill when a more specific tool should be used.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
This codebase presents its descriptions, generated prompts, and command-line help primarily in Chinese, which constitutes a language/locale constraint. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.

Vague Triggers

Low
Confidence
87% confidence
Finding
The 'When to Use' section lists broad categories without corresponding non-trigger boundaries, so many ordinary requests about writing, coding, design, or analysis could match even when the user is not asking for prompt generation. This weak scoping can lead to accidental invocation and routing errors, though the skill content itself does not appear to contain direct payloads or privilege-seeking behavior.

Static analysis

No suspicious patterns detected.